Conference PaperPDF Available

Description and future trends of ICT solutions offered towards independent living: The Case of LLM project


Abstract and Figures

Due to the increasing elderly population, healthcare systems able to promote independent living are regarded as an emerging market. Despite the significant advances aiming to support senior citizens, several issues have to be addressed in order to enable older people to live independently and to form living cells of our society. Aiming to contribute to the research of elderly care, this paper reports the open issues that should be taken into consideration in order to provide a technological solution towards Ambient Assistive Living (AAL). After reviewing the most prominent European funded projects, it presents an example of integrated elderly healthcare platform and finally attempts to highlight the future trends which should be employed in order to face with success the social and financial phenomenon of ageing population.
Content may be subject to copyright.
Description and Future Trends of ICT solutions offered
towards Independent Living: the case of LLM project
Christos A. Frantzidis
Lab of Medical Informatics, Medical
School, Aristotle University of
Thessaloniki PB 323,
54124, Thessaloniki, Greece
+30 2310 999 332
Panagiotis D. Bamidis
Lab of Medical Informatics, Medical
School, Aristotle University of
Thessaloniki PB 323,
54124, Thessaloniki, Greece
+30 2310 999 310
Due to the increasing elderly population, healthcare systems able
to promote independent living are regarded as an emerging
market. Despite the significant advances aiming to support senior
citizens, several issues have to be addressed in order to enable
older people to live independently and to form living cells of our
society. Aiming to contribute to the research of elderly care, this
paper reports the open issues that should be taken into
consideration in order to provide a technological solution towards
Ambient Assistive Living (AAL). After reviewing the most
prominent European funded projects, it presents an example of
integrated elderly healthcare platform and finally attempts to
highlight the future trends which should be employed in order to
face with success the social and financial phenomenon of ageing
Categories and Subject Descriptors
D.2.4 [Software/Program Verification]: Validation, Reliability,
Correctness proofs. D.2.6 [Programming Environments]:
Integrated environments, Interactive environments H.1.2
[User/Machine Systems]: Human factors, H.3.4 [Systems and
Software]: Performance evaluation (efficiency and effectiveness)
General Terms
Management, Measurement, Performance, Design
Experimentation, Human Factors, Standardization,
Ageing, Ambient Assistive Living, Mental Health,
Neurophysiology, Skin Conductance, Integrated ICT Platform
As the ageing population continues to grow rapidly, the
establishment of technological innovations which will meet the
needs of older people becomes more demanding. Furthermore,
taking into account the modern social trends which are
encountered in western societies and resulted in demanding
working environments as well as in the creation of dispersed
families, the development of elderly healthcare systems is
regarded as an open research issue closely related to an arising
and expanding market. Potential e-Health solutions may be
focused on the alleviation of everyday life by means of remote
monitoring and notification in case of emergency in order to
enhance their safety sense and to promote their chances of
independent living.
However, several issues have to be confronted in order to provide
senior citizens greater support towards their independent living.
More specifically, the particular needs of elderly people form a
lifestyle pattern which greatly differs from the daily activities of
the young and middle-aged adults. Therefore, their interaction
with the society is problematic. As a consequence, isolation from
their surrounding environment is a common feeling among senior
citizens. Their negative emotional mood is further enhanced by
the experience of loneliness since they often miss their own
relatives. Recent technological advances may be a promising
solution to the aforementioned difficulties since they can improve
the daylife of older people and to facilitate their living at home.
On the other hand, the adoption of technology to elderly
healthcare systems is doomed to encounter major problems since
the vast majority of this population category is unfamiliarized
with the available communication and interaction services.
Therefore, special care should be given to the development of an
easily accessible, user-centric platform which will provide
according to the needs of elderly users an innovative solution
which is validated and fitted under realistic scenarios. Regarding
the constantly increasing amount of senior citizens, the wide
adoption of approaches aiming to enhance both independent
living and active ageing is expected to take place during the next
Recent advances in the medical informatics field aim to offer new
friendly communication forms which may also serve as a real
shelter to older people living at their own homes. Nowadays, the
internet is not regarded any more as a “passive source of
information”, but as a “living-platform” which offers co-operative
abilities to the information seeking and to the knowledge
extraction. Among the emerging web-based applications of this
newly introduced communication era are the social-networking
sites, wikis, blogs and folksonomies. So, older users or patients
Permission to make digital or hard copies of all or part of this work for
personal or classroom use is granted without fee provided that copies are
not made or distributed for profit or commercial advantage and that
copies bear this notice and the full citation on the first page. To copy
otherwise, or republish, to post on servers or to redistribute to lists,
requires prior specific permission and/or a fee.
Petra’09, June 9–13, 2009, Corfu, Greece.
Copyright 2009 ACM ISBN 978-1-60558-409-6…$5.00.
may form groups according to their personalized needs and to
share their experiences with other patients suffering from common
problems [1]. Moreover, they could be informed from health
specialists by means of multimedia material [2] or to have access
in high quality journal articles [3].
Furthermore, virtual interaction environments may be utilized in
order to enhance the social activity of the senior citizens and to be
combined with the aforementioned technologies in order to
increase the impact of social-networking. These types of services
are expected to promote common activities between the members
of the virtual community who could interact using the internet for
sharing feelings and discussing their ideas. Specific policies guide
their interaction towards information exchange in order to fulfill
their purposes which may be virtual psychotherapy groups or
knowledge extraction and social activity promotion. Despite the
fact that initial communities adopted more primitive forms of
communication like chat-rooms, instant messengers or e-mails,
more innovative types of interaction, which employ virtual reality,
are now available like virtual worlds [4].
The main challenge that faces the adoption of such environments
remains the system acceptance from the older users. Towards this
direction, human-like characters (avatars) have been introduced in
order to make the application they are part of to appear more
natural. As a consequence, the interaction with the system is
getting closer to the one between two human beings enhancing
thus its acceptance ratio [5]. Furthermore, the use of avatars may
result to a better understanding by the users in case it possesses
human behavior through speech, mood, gestures, emotions, etc.
Another important issue that should be addressed is the remote
monitoring of elderly people in order to secure their safety by
identifying imminent hazards and detecting common elderly
accidents like falls or mobility difficulties. This is mainly
achieved by means of sensor networks like accelerometers or
other biometric sensors [7]. Except from the early recognition of
sudden physical declines, smart elderly healthcare systems should
also deal with the changes in the user’s cognitive state as revealed
by behavioral and emotional deviations. Therefore, except from
the aforementioned solutions derived from the health informatics
field, the technological systems which interact with the senior
citizens should be envisaged with affective computing techniques
that collect and process neurophysiological measurements [8].
Moreover, recent technological improvements facilitate such
applications through the use of wearable and miniaturized sensors
[9], which may be adopted for the continuous collection in a
minimally obtrusive way of various physiological and ambient
data in a variety of conditions. Then, pattern recognition and data
mining techniques could be integrated in order to dynamically
process and analyze the collected data in order to extract the
subject’s mental state [10] or arousal level [11]. The results may
be described in a structured way through XML format [12] in
order to adjust the avatar’s facial expressions and its speech
according to the situation the user faces [13].
The aim of this paper is to review the technological advances and
solutions utilized for supporting senior citizens according to their
needs as well as with the recent social trends of modern
communities. The description of these advances is attempted to
combine the medical informatics and communication field with
the domain of the applied neuroscience. Particular emphasis is
given on the dynamic processing and visualization of
neurophysiological data which comprise a powerful tool for the
detection of the mental health status and to assess cognitive
declines. The architecture scheme of the European project titled as
“Long Lasting Memories (LLM)” is analyzed in order to provide
a view of the future advances in the field of elderly care systems.
So, in the remaining of this paper a brief description of other
related research projects funded by the European Union is given
in section II. The neuroscience findings regarding the emotional
processing are described in section III, while section IV provides
an overview of the LLM architecture. Finally, future trends in the
field into consideration are discussed in section V.
2. State of the art in ICT solutions for the
During the past years serious efforts have been conducted in
applying the aforementioned technological advances to alleviate
the difficulties of older people. Particular interest was given in the
field of Ambient Assistive Living (AAL) since it is an issue with
important social and financial consequences. The AttentiaNet
project aims to provide a new model for the assistance of senior
citizens by including location mobile capabilities and broadband
tele-communications except from the basic services [14]. Special
care was given to the fact that older people are unfamiliarized
with the modern technological equipment. Therefore, the
components of the proposed solution were selected in order to be
understandable and easy to use. This approach aims to provide an
initial attempt for independent living while simultaneously
dealing with the common problems of social isolation and
insecurity feelings. Future extensions of this project may form an
integrated healthcare system for older people or persons with
An alternative framework of tele-assistance services which aims to
enhance the security of elderly not only in their home as the
previous case is introduced by the MobilAlarm project [15]. Its
objective is to supply the elderly with a small, light and easy to
handle device which calculates the user’s position by means of a
Global Positioning System (GPS) technology and then transmits it
to the service centre, even in the case the person in need cannot
describe his or her exact position.
A more integrated attempt to enhance the independent living of
senior citizens by providing them innovative services through a
cost-optimized technological platform is investigated by the
OLDES project [16]. This system aims to secure older people who
live alone by means of medical sensors, tele-medicine applications
and a knowledge management system which will investigate their
life-style profiles. However, entertainment services will also be
provided in order to improve their life quality.
Another important aspect is that of remote tele-monitoring of
elderly people in a non-invasive way in order to diagnose
accidents which may result in physical decline. Towards this
direction, the CONFIDENCE project aims to identify falls as well
as short or long-term unexpected behaviors which may be indices
of health deterioration [17]. Crucial issues related with the
acceptability of this system are its cost as well as its level of
Except from regarding the physical status of senior citizens,
several European projects have been focused on the mental health
of elderly people attempting to alleviate the difficulties from
certain deficits which are common among this population
category. The ENABLE project investigated the needs of people
suffering from Alzheimer and utilized innovative, smart services
which may facilitate the patients to perform their daily tasks [18].
Furthermore, system components were developed in order to
enhance the memory of older people as well as with their
communication abilities. Moreover, natural and comfortable
interfaces were utilized for entertainment purposes by means of
multimedia material.
The SOPRANO project aims to provide a system which facilitates
older people to face their living at home enhancing their comfort
and safety. Among its main objectives is the user’s independence
[19]. Therefore, emphasis is given to the particular needs of each
user in order to enable them to maintain their autonomy and to
enhance their social interaction. The proposed framework seems
to deal with the acceptance problems in a more robust way than
the previous ones, since its architecture is modular and the
provided services are scalable. Furthermore, the various system
components may complement each other according to the user
needs. Therefore, each user may form a personalized SOPRANO
system as he wishes. The aforementioned and other related EU
funded projects are summarized in the following table:
Table 1 Brief Description of EU funded projects dealing with
the enhancement of independent living and elderly care
Short Description
AttentiaNet Extension of the traditional tele-assistance
model by the inclusion of understandable and
easy to use location mobile capabilities and
broadband communication
Seniority Provide an integrated tele-monitoring
framework in order to facilitate the
independent living of elderly people by
enhancing their communication and
entertainment abilities, increasing their
mobility and decreasing their social isolation
MobilAlarm Both in-door & out-door tele-assistance
enhancement in case of emergency by
providing a small GPS equipped device
Netcarity Development of technological solutions
towards the life quality improvement, the
social interaction enhancement, elderly people
independent living an
d safety
INHOME Facilitate the life quality improvement of
elderly people by providing technologies for
the management of entertainment equipment
and home automation systems in order to
increase their sense of safety and autonomy
OLDES Enhance the Independent Living by using tele-
assistance, tele-medicine & tele-entertainment
devices in order to secure older people while
simultaneously improving their life quality
Confidence Detection of health deterioration indices in a
non-invasive and cost-optimized way
Smiling Diminish age-related motor impairments by
utilizing training procedures in real-life
Companionable Combination of a mobile robot with a smart
home in order to provide high quality elderly
care ad to enhance the person’s interaction
TeleCARE A multi-agent tele-supervision system aimed to
improve the quality of life and elderly care by
focusing on virtual communities
ENABLE Development of a personal, user-centerd
system focused on the mental health of older
people suffering from dementia
SOPRANO Modular system architecture for enhancing life
independence and social interaction of older
people during Independence Living in a safe
and comfort way
3. Neurophysiology of emotional processing
visual stimuli
According to the nowadays widely accepted cognitive approach,
the human brain plays a key role to the emotional processing,
since it regards each experienced situation as either pleasant or
unpleasant. Therefore, the current emotional theory is based on
two brain mechanisms, which are the appetitive and the defensive
one [20]. They have evolved in order to assure the physical
survival and are implemented by neural circuits in the brain.
Consequently, emotions could be described by means of affective
valence and arousal. Valence refers to the direction of behavioural
activation according to the motivational system induced by the
stimulus. Arousal represents the activation level elicited by the
emotionally evocative stimulus [21].
Based on the above considerations, several efforts have been
conducted in order to explore the ways that valence, arousal and
gender modulate the responses of both the central and the
autonomic nervous system. Among them worth mentioning is the
AFFECTION project, which was a collaborative project between
the Medical School of the Aristotle University of Thessaloniki,
Greece and the Brain Science Institute of RIKEN in Japan [22].
Its objective was to explore the neuronal changes occurring due to
discrete emotions. These emotions were elicited by passive
viewing of emotional evocative pictures selected from the
International Affective Picture System (IAPS), which provides a
set of normative pictures that differ according to their arousal and
valence dimensions and may be freely used by experimental
procedures [23].
According to the protocol, healthy young adults (14 men and 14
women) are being exposed to emotional evocative stimuli
presented on a PC monitor. Each picture was characterized by a
specific (L for Low, H for High) Valence-Arousal dimension
(HVHA, HVLA, LVHA and LVLA). There are 40 trials from
each one of the four affective space conditions. Consequently, the
participant passively views 160 pictures. During the first phase of
the experiment, each block category is presented in a random
order, while in the second phase each one of the 160 pictures is
presented randomly regardless of its block category. The picture’s
presentation duration was set at 1 second, while between two
successive stimuli a central fixation cross appears for 1500
milliseconds. During the experiment, the recorded data were 19-
channel electro-encephalogram (EEG) according to the 10-20
International System and electrodermal activity.
After the pre-processing, for each subject the averaged waveforms
were obtained from each one electrode site as well as for the skin
conductance signal. A typical EEG waveform is depicted in
Figure 1, where the main Event-Related Potentials (ERPs) are
Most of the aforementioned ERP components are being
modulated by the arousal, valence or by the subject’s gender.
Furthermore, in some cases interactions of the aforementioned
variables also occur. For example in Figure 2, the amplitude of the
P300 is modulated by the stimulus arousal whereas negative
pictures elicit more prominent N200 components.
Figure 1 A typical ERP waveform time locked to the stimulus
onset. The main ERP components are characterized by either
P for positive or N for negative peaks and the time that occur
after the stimulus onset
Figure 2 Emotional modulation of the ERPs recorded in the
central electrodes
Early findings from the specific project have revealed that
emotional processing of visual stimuli is a complex task which
differs between males and females. Moreover, there are certain
neural circuits either located in specific brain regions or widely
dispersed which are being affected by the valence dimension or by
the arousal dimension in certain time intervals during the
processing procedure [24].
The level of statistical importance of the aforementioned variables
during different temporal intervals is visualized in Figure 3.
The data of the electrodermal activity provided autonomic indices
dealing with the emotional processing. Early results from the first
phase, which are visualized in Figure 4, revealed that negative
stimuli and especially fear-related pictures elicit faster responses
than the positive ones, while subjects respond stronger to the
highly arousing events [24].
Figure 3 Time dependent visualization of the statistical
importance of the valence, arousal and gender variables across
the different electrode sites
Figure 4 Skin conductivity responses during Phase 1
In the case of the second phase, the completely random
presentation of the IAPS pictures resulted in a very strong arousal
effect. The aforementioned results are visualized in Figure 5:
Figure 5 Skin conductivity results during passive viewing of
IAPS pictures in a complete random order reveal mainly
arousal modulation of the SCR amplitude
Recent studies have investigated whether advancing age affects
the neural substrates of emotion. Data from event-related
functional magnetic resonance imaging were used in order to
assess whether amygdale activation in response to emotional
stimuli alters with age [25]. Seventeen young adults (M=23.41,
SD=3.24; 8 females) and seventeen older adults (M=78.41,
SD=4.86; 8 females) participated in the study. The findings
indicate that with age, the amygdale may show decreased
reactivity to negative emotion. Therefore, elderly people pay less
attention to negative emotions and become less likely to
remember them, since their encoding is diminished as soon as
they experience it. On the contrary, amygdale reactivity is
maintained or even enhanced during the experience of pleasant
situations. Another finding of this study indicates that participants
with similar behavioral responses demonstrated the same
activation patterns regardless of their age. The aforementioned
findings demonstrate that behavioral factors also influence the
brain activation patterns. Furthermore, aging does not reflect a
global functioning decline of amygdale activity but a
responsiveness shift towards to pleasant stimuli. The subjects
viewed pictures from the International Affective Picture System
(IAPS) [23].
Another study employed Event-Related Potentials (ERPs) from 21
electrode sites [26]. The study participants were divided into two
groups according to their age. The stimuli differed to their arousal
dimension, being either high or low. The picture display was
performed by means of a Rapid Serial Visual Presentation
(RSVP). The presentation rate was set at 3 Hz. There were no
inter-stimulus intervals and the arousal sequence was altered. An
Early Posterior Negativity was analyzed in two time windows
(168-232 ms and 232-296 ms respectively). This peak component
was associated with high arousal regardless of the age. However,
elderly subjects produced delayed responses in comparison with
the younger adults during the first interval. This effect was not
correlated with the arousal dimension but with the early visual
emotion discrimination. Moreover, young participants produced
overall more intense brain responses. According to these findings,
aging results to delayed initiation of affective discrimination as
well as with overall decline to the response magnitude without
affecting any other emotional parameter.
According to these studies, different aspects of emotion show
differential changes as a result of aging. Towards to a more
integrative view of the neuronal mechanisms involved in
emotional processing, physiological recordings of the autonomic
nervous system due to emotional stimuli should also be
considered. Therefore, another study used IAPS pictures during
heart rate, skin conductance and electromyographic (EMG)
recordings [27]. The participants were divided into three groups
(old, middle-aged and young) according to their age. The study
hypotheses were that the group of young participants would
demonstrate lower subjective responses to the emotional stimuli.
Moreover, elderly people are assumed to respond with lower
intensity. However, these responses is hypothesized to be
correlated with the subjective ratings and to bear the same
relationship in all groups. The first hypothesis is valid since both
older and middle-aged people showed enhanced affective
judgments. Similarly, these two groups demonstrated dampened
physiological responses. The fact that middle-aged subjects follow
the response pattern of elderly people may be indicative of a
maturational process rather than a biological decline. The last two
hypotheses were also valid, demonstrating the relationship
between slide ratings of emotional dimensions and autonomic
4. The LLM Approach
The Long Lasting Memories (LLM) consortium is a European
effort comprised of twelve partners from six different countries
aiming to support elderly people and their families towards
independent living and active ageing. Therefore, a
multidisciplinary team from various technological and service
fields as well as with public authorities has been employed in
order to provide an integrated and user-centric platform which
may enable this population category to live in an autonomous way
and to work or to interact with the society despite facing age-
related impairments. The project’s approach towards the
achievement of its goal is to combine the providing of the
traditional tele-monitoring services for the detection of common
threats with the simultaneous mental and physical training in
order to increase the self-esteem of older people and also to
alleviate the symptoms of mental deficits or even to reduce the
possibilities of mild cognitive impairment or dementia occurrence.
An important aspect of the framework is the effort to achieve its
goals in a cost-optimized way which will result in an easily
accessible and widely available technological solution which will
be affordable for the vast majority of elderly people and care
providers. Another crucial issue is to test the LLM approach in
real life situations so as to validate its practical features by
forming a set of requirements and functional specifications.
The LLM proposed solution is consisted of home automations
aiming to support the daily activities of people with cognitive
problems. Furthermore, in case of an emergency, an elaborate
distributed sensor network is responsible to call help through
public telephone lines. Moreover, technological equipment may
be installed to their living places such as homes or institutions in
order to provide simultaneous and personalized mental and
physical training in an accident-free way. The personalization of
the training program is a vital feature of the proposed solution
since it is expected to result in optimized performance according
to the person’s health status and needs.
The LLM training approach is consisted of two axes. First of all,
sensory training is regarded as a robust way of slowing down the
symptoms of cognitive deterioration and mild dementia. On the
other hand, the corporal activation influences in a positive way
the physical status. So, the combined moto-sensory training
creates a comprehensive system for the elderly.
Towards the implementation of the aforementioned services, the
LLM system utilized state-of-the-art hardware and software
technological solutions. More specifically, the user may interact
with the system by means of two distinct user interfaces. The
basic and most widely used is that of the Local User Interface
(LUI), which actually is a touch screen. When using the specific
interface, elderly people have full access to the system
functionalities such as monitoring of both the cognitive and the
physical exercising as well as with the home environment
management. The latter function involves the use of actuators
which are remotely employed in order to provide daily activity
supporting features like opening windows, doors and blinds. On
the other hand, the Remote User Interface (RUI) is activated in
case of an emergency with the responsibility of communicating
with the relatives, care takers or authorities. Towards this goal, it
employs two different sensor components. The role of the first
sensor category is the movement monitoring inside the house.
Therefore, a distributed sensor network consisted of wirelessly
connected sensors is utilized in order to extract moving patterns
and then to detect deviations from these patterns. In such cases the
RUI interface is activated. The second type of sensors is
responsible for the detection of forgotten switched on electrical
appliances by measuring the voltage and current consumption of
each one appliance. Consequently, these two sensor categories
may guarantee the safe living of the elderly inside their home
environments without needing exclusive intensive care. Finally,
the core elements of the proposed architecture are an embedded
processor and a general purpose PC which are employed in order
to co-ordinate and to manage the AAL environment. A possible
scenario which highlights their applicability is the execution of
the cognitive training software and then the tasks of storing and
processing the physical training performance information. The
LLM architecture is visualized in the following figure:
Figure 6 The LLM proposed architecture for AAL living of
elderly people
Regarding cognitive training, the initial software choice is that of
BrainFitness [28], since it provides exercises aimed to speed up
auditory processing, improve working memory and encourage the
production of chemical substances which are of vital performance
in memory processes. Most of the utilized mental tests involve
sounds for the induction of temporal or frequency sensory
discrimination or to enhance auditory and visual short-term
memory. Dealing with the physical exercise, specific equipment
could be used according to the user physical profile. More
specifically, people with serious disabilities may employ
ergometers since they require minimum physical exertion and may
be used in normal sitting position. In the case of elderly with
moderate disabilities the most suitable choice is that of recumbent
bikes, since they are equipped with safety mechanisms such as
specifically designed chairs and firm stabilization thanks to the
back of the seat and the side handles. Consequently, older people
should not be afraid of falling during practicing, while they can
safely interrupt their exercise when they wish. Moreover, elderly
people of younger age or in better shape may use treadmills and to
simulate a virtual walk. The existing safety specifications have
been further enhanced by means of the monitoring systems. The
performance of elderly people is processed by the LUI component
which provides feedback to the users by means of motivation
messages and performance indicators.
Figure 7 Integration of the main technological solutions
offered by the LLM platform
Special care should be given in the integration of the various
heterogeneous sub-components utilized by the LLM platform.
More specifically, the physical training equipment is regarded to
provide input signals dealing with the user’s performance on these
devices. This type of information is then transmitted to the Central
Management System (CMS) and is digitized. Taken into
consideration the fact that these signals provide an index of the
user’s current physical status, they may be correlated with
previous physical markers in order to conclude about the physical
condition of the user. Afterwards, these data may be stored on a
local database and the resulting knowledge will be forwarded to
the eHome environment for display. It should be mentioned that
during the physical exercise, the sensor network may track the
movements of the user in order to identify potential problems and
to act according to the problem’s significance.
Unlike the physical training procedure, the cognitive training
procedure is more complicated due to the fact that it involves the
integration of the eHome environment with the Cognitive
Training Component (CTC). More specifically, the CTC should
notify elderly people for the training initiation by means of a
message which is displayed by the LUI. Then, the user accepts the
initiation of the process and the CTC employs the LUI in order to
present its training content. The user’s response is performed
through the LUI. Then, the CTC processes the obtained response
and stores its value into the database. Finally, it provides the
appropriate feedback to the user and continues with the training
content. The visualization of the aforementioned integration
scenario is provided in Figure 7.
5. Discussion
The domain of elderly healthcare technological platforms is one of
vital importance for the European population. Senior citizens
form a major category which may be excluded in the forthcoming
years from the emerging technological advances occurring in the
fields of communications, information and entertainment. This
growing gap may result in social occlusion, mental decline and
cause feelings of loneliness. Taken also into consideration that
several mobility difficulties and physical impairment occur due to
ageing, several social and financial problems are posed.
Despite the identification of the aforementioned problems and the
serious research efforts focused on independent living solutions,
the proposed frameworks have encountered serious problems.
Among them, maybe the most important is that of the
familiarization difficulties that older people encounter when they
try to use state-of-the-art hardware and software solutions.
Therefore, the acceptance ratio of such approaches remains till
now at low level.
Moreover, there are sub-groups with different needs and
characteristic features among the elderly population. A promising
approach seems to be that of modular or scalable architectures.
These technological approaches offer the ability to form
personalized frameworks in order to satisfy the user needs.
However, particular emphasis should also been given to the user
interfaces which are used for the interaction with the system.
Regarding the fact of facing difficulties with the technological
devices, software developers should adopt the new advances in
the human-computer interaction field in order to get it closer to
the one between two human beings [13]. Therefore, avatars able
to change their facial expressions and to adapt their behavior
according to the user’s mood may be adopted in order to facilitate
elderly people to interact successfully with the technological
platforms utilized to support their independent living.
Furthermore, such systems should deal with every aspect of the
user’s daily life and not only to focus on the tele-monitoring
services which aim to protect him by identifying imminent
hazards or to detect common accidents. Therefore, a potential
framework, except from the aforementioned features, should also
provide innovative entertainment solutions by employing internet
applications such as virtual communities and interactive games.
Moreover, its core goal should be the maintenance of a
satisfactory health state. The Long Lasting Memories (LLM) is an
integrative approach based on the above specifications since it
aims to prevent cognitive impairments such as mild dementia by
utilizing several mental tasks as well as with physical exercises.
However, except from the memory enhancement other cognitive
processes should also be taken into consideration. Among them,
the emotional processing is one of particular importance and
directly related with the overall cognitive performance [29] and
with the person’s ability to interact with other people [13].
Moreover, the use of neurophysiological recordings from both the
central (EEG) and the autonomic (electrodermal activity) nervous
system is expected to provide more reliable indices of the user’s
mental health status, while it may form a validation method for
evaluating the performance of the cognitive training provided by
the LLM technological platform.
[1] Patient Like me,
[2] Summaries of the Latest Medical Research,
[3] Journal of Medical Internet Research: Web Evaluation at the
US National Institute of Health,
[4] SecondLife,
[5] Bamidis, P. D., et. al., “Multi-channel physiological sensing
of human emotion: insights into Emotion-Aware Computing
using Affective Protocols, Avatars and Emotion” in Proc. Of
Medinfo 2007.Brisbane, Australia, 2007, pp.1068–1072
[6] Reeves , B., Nass C., “The Media Equation: How People
Treat Computers”, Cambridge Univ. Press, 1996.
[7] Konstantinidis, E.I, Bamidis, P.D, Koufogiannis, D.:
Development of a Generic And Flexible Human Body
Wireless Sensor Network. In: 6th European Symposium On
Biomedical Engineering (ESBME 2008), Chania, Crete
Island, Greece
[8] Bamidis, P.D, Papadelis, C., Kourtidou-Papadeli, C., Pappas,
C., Vivas, A.,: “Affective computing in the era of
contemporary neurophysiology and health informatics”,
Interacting with Computers, 2004, 16(4):715-721.
[9] Picard, R.W and Healey, J.: “Affective Wearables. Personal
and Ubiquitous Computing”, vol.1, no. 4, pp. 231-240
[10] Frantzidis, C.A, et al.: “On the classification of emotional
biosignals evoked by affective pictures: an integrated data
mining based approach”, submitted in IEEE Transactions on
Information Technology in Biomedicine, 2008
[11] Frantzidis, C.A, Lithari, C., Vivas, A., Papadelis, C., Pappas,
C., Bamidis, P.D : “Towards Emotion Aware Computing: a
Study of Arousal Modulation with Multichannel Event
Related Potentials, Delta Oscillatory Activity and Skin
Conductivity Responses”. In: 8
IEEE International
Conference on BioInformatics and BioEngineering (BIBE
2008), pp. 1-6, Athens, Greece (2008)
[12] Luneski, A. and Bamidis, P. D.: “Towards an Emotion
Specification Method: Representing Emotional Physiological
Signals”. In: 20th IEEE International Symposium on
Computer-Based Medical Systems (CBMS'07), pp. 313-320,
Maribor, Slovenia (2007)
[13] Bamidis, P. D., et al.,: “An integrated approach to emotion
recognition for advanced emotional intelligence”. In HCI 09,
San Diego, USA, to be presented
[14] AttentiaNet,
[15] MobilAlarm,
[16] OLDES,
[18] ENABLE,
[20] Lang, P.J., Bradley, M.M. and Cuthbert, B.N, “Emotion,
Motivation, and Anxiety:Brain Mechanisms and
Psychophysiology”, Biological Psychiatry, vol. 44, 1248-
1263, 1998
[21] Lane, R.D., Chua, P.M-L. And Dolan, R.J., “Common
effects of emotional valence, arousal and attention on neural
activation during visual processing of pictures”,
Neuropsychologia, vol. 37, issue 9, 989-997, 1999
[23] Lang, P.J, Bradley, M.M and Cuthbert, B.N, “International
Affective Picture System (IAPS): Technical Manual and
Affective Ratings”, NIMH Center for the Study of Emotion
and Attention, 1997
[24] Lithari, C., et al., “Are females more sensitive to emotional
stimuli?A neurophysiological study across arousal and
valence dimensions”, submitted in Brain Topography
[25] Mather, M., et al., “Amygdala Responses to Emotionally
Valenced Stimuli in Older and Younger Adults”,
Psychological Science, vol. 15, no. 4, pp. 259-263, 2004
[26] Wieser, M.J, et al., “Is emotion processing affected by
advancing age? An event-related brain potential study”,
Brain Research, vol. 1096, issue 1, pp. 138-147, 2006
[27] Burriss, L., Powell, D.A and White, J, “Psychophysiological
and subjective indices of emotion as a function of age and
gender”, Cognition & Emotion, 21:1, pp. 182-210, 2007
[28] Brain Fitness,
[29] Picard, R.W. et al.: Affective learning – A Manifesto. BT
Technology Journal, vol. 22, no. 4, 253-269 (2004)
... One application area where new innovative services are being developed is health promotion. Two examples of this are independent living for elderly (Frantzidis and Bamidis, 2009) and medical support in homes for people with diabetes (Kanstrup, Bertelsen, Glasemann and Boye, 2008). In this paper we report from an on-going design research project aimed at designing digital peer support (DPS) for children cured from cancer. ...
Conference Paper
Innovative design targets new user groups and application areas. One example is health promoting digital services. In such design contexts it is essential to take social and ethical challenges into consideration. In this paper we report from an on-going design research project aimed at designing digital peer support (DPS) for children cured from cancer. Peer support can meet the children's imperative need for social support. However, the design context is sensitive and gives rise to ethical challenges and considerations. We illustrate how participatory design (PD) activities can be designed to handle, ethical challenges when designing for and with children. We present lessons learned, including using familiar activities, using personas and including healthy children when possible. Further, we reflect on the need to proactively design an ethical perspective into the entire design process, introducing the concept Ethics in Design.
... Innovative digital services are designed and implemented in a variety of contexts, targeting new user groups and application areas. For example, digital services have been developed to promote independent living for elderly [1] and for medical support in homes for people with diabetes [2]. Innovative digital design is also implemented in numerous products. ...
Conference Paper
Digital innovation is rapidly reshaping society, affecting fundamental aspects of our everyday activities and lives. This development is accompanied with benefits as well as social dilemmas. In this paper we approach this class of challenges in IS digital innovation research. We investigate how social challenges are attended in research agendas, and reflect upon social challenges emerging from a digital service innovation project. Based on the empirical case, we present a scenario that illustrates how social challenges can unfold in digital service innovation. The case exemplifies three conflicts of interest that are used to discuss implications for the research agendas for digital innovation. We propose that explicit attention is paid to social and ethical challenges, taking a large scale and interdisciplinary approach on social and ethical challenges in digital ecosystems. © IFIP International Federation for Information Processing 2014.
... Internet should be active not in passive living form. Thus behavioral and emotional and deviations are taken as system input [15]. ...
... URING the last few decades, senior population and life ex- 26 pectancy have been increasing constantly, thereby posing 27 the need for preservation of autonomous living for longer pe- 28 riods of time [1]. Ambient-assisted living (AAL) technologies 29 have become a contemporary trend towards the promotion of 30 independent living among the elderly and the disabled [2]. Nu- 31 merous services have been proposed [3] as part of AAL research 32 and pilot projects, such as: health monitoring and detection of 33 health abnormalities [4], [5], emergency alerting [6], [7], early 34 prognosis of chronic conditions [8]–[11], and enablement of 35 actions in order to alleviate or prevent disease symptoms [12]. ...
Full-text available
Artificial intelligence and decision support systems offer a plethora of health monitoring capabilities in Ambient Assisted Living (AAL) environment. Continuous assessment of health indicators for elderly people living on their own is of utmost importance, so as to prolong their independence and quality of life. Slow varying, long-term deteriorating health trends are not easily identifiable in seniors. Thus, early sign detection of a specific condition, as well as, any likely transition from a healthy state to a pathological one are key problems that the herein proposed framework aims at resolving. Statistical process control concepts offer a personalized approach towards identification of trends that are away from the atypical behavior or state of the seniors, while Fuzzy Cognitive Maps knowledge representation and inference schema have proved to be efficient in terms of disease classification. Geriatric depression is used as a case study throughout the paper, so to prove the validity of the framework, which is planned to be pilot tested with a series of lone-living seniors in their own homes.
Full-text available
Older people are fragile people who need the support of other younger people and even help from new technologies to improve their living conditions. The issue of improving the living conditions of senior citizens through intelligent computer systems is discussed in this article. We present a state of the art on intelligent computer systems techniques, in particular ontologies for improving the living conditions of seniors, in order to highlight some shortcomings and take a position accordingly.
Health care systems are in transition to citizen-centered care with focus on prevention, proactive and personalized services and healthy lifestyles. Innovative technologies enable citizens’ empowerment and allow them to manage their complete health and wellness. Citizen-centered tools collect life-long cross-institutional information and data from health care providers and citizens. From the health care organizations viewpoint the new paradigm implies changes in the ways how the services are produced, how they are offered for use and in the contents of the services. Research with the citizen-centered health paradigm has been active and many significant results have been achieved, for instance improvements in citizens’ lifestyle, weight loss, reduction of the duration of hospitalization, better accessibility of health related information and improved communication between the care providers. Based on our literature review we present in this chapter the approaches, achievements, barriers and challenges of citizen-centered health paradigm. We propose a new innovative approach to build the next generation, collaborative health information space that links the care providers and citizens together and helps them to access the distributed health resources any time anywhere. The visional, sustainable citizen-centered health environment offers means to gradually migrate from the current situation to a citizen-centered care environment where citizens have a participatory role in health care activities.
Objective Positive external pressure is said to decrease transmural pressure; negative pressure in the pleural cavity is widely believed to result in negative pressure in systemic chest veins. The discrepancy between erect column height and foot venous pressure has been explained on this basis. Methods These core concepts rest on static closed models that may not be appropriate. This study examined the effects of external pressures in a dynamic open model that may better reflect in vivo conditions. Flow in a Penrose drain enclosed in a chamber that could be positively or negatively pressurized was used. Input and output reservoirs with pressures in the physiological range provided flow. Flow and pressure were monitored in horizontal and erect models with modifications to suit particular experiments. Results The discrepancy between foot venous pressure and erect venous column height was shown in this experimental model to be a result of two flows in opposite directions (superior and inferior vena cavae) meeting at the zero reference level at the heart; the upper column pressure therefore does not register at the foot. Positive external pressure results in slowing of velocity with conversion to pressure. Internal and transmural pressures therefore do not decrease. Negative external pressure has only a marginal effect on flow; importantly, internal pressure does not become negative. In an experimental set-up it was shown that negative pressure in chest veins was not necessary for air embolism to occur. Conclusion Persistent negative pressure in systemic chest veins probably does not occur. The reason for the discrepant foot venous pressure is likely to be a result of dynamic flow and not negative pressure in chest veins. External positive pressure results in slowing of velocity but the transmural pressure remains largely unchanged.
Varicose veins of the lower limbs arising from the pelvis stay insufficiently evaluated and treated. Their alimentation by « pelvic escape points », whose prevalence is about 10 %, is now well described. These pelvic escape points are easily accessible with a rigorous duplex scan ultrasound exploration. The treatment of lower limbs superficial venous insufficiency must include these reflux points.
Full-text available
The first part of this review article provides the physiologic background that sustained the CHIVA principles development. Then the venous networks anatomy and flow patterns are described with pertinent sonographic interpretations, leading to the shunt concept description and to the consequent CHIVA strategy application. An in depth explanation into the hemodynamic conservative cure approach follows, together with pertinent review of the relevant literature.
Full-text available
In the current work, we present our position towards the modeling of a decision support system for health assessment and prevention of risky situations in the life of seniors. A two-layer architecture based on the Fuzzy Cognitive Maps (FCMs) methodology is considered as the main tool to encode medical knowledge and reason about the health status of seniors. This is the initial step, since outputs of several discrete FCM models are then combined to form the input concepts for an upper level schema (the health status of the senior) of upper-level concepts and relationships, so as to infer about recommended individualized therapies and interventions that would help therapists to prevent risky situations and enhance the independence and quality of life of the seniors. A modeling sample of the depression assessment is presented at the first level of the proposed architecture, while am integration schema of the proposed approach provides a view of our future extended model.
Full-text available
Wireless sensor networks on human body have become essential in the field of patient monitoring. The fact that completely non-invasive sensors can be used attached on clothes, facilitates measurements in daily tasks. The aim of this paper is to demonstrate the approach we followed upon developing a generic and flexible patient tele-monitoring system based on custom sensor devices and a communication control unit (CCU). A sensor device consists of the measurement control part (microcontroller) and the sensing part (be it commercial or homemade sensors). The CCU plays the role of the master device of the wearable network and is based on a microcontroller and a Bluetooth module. The CCU scans all possible attached sensors on the bus of the network and constructs XML files based on the sensor devices and the network structure. In addition a software suite has also been developed in order to i) manage the different protocols and projects, ii) manage the operating system service and iii) provide different representations/visualizations of the signals (online or offline) in 2D graphs, FFT or 3D human model in the appropriate environment. At the PC side, the operating system service utilizes the XML descriptions in order to acquire the measurement from the CCU and store them in a database. The usefulness of the system is demonstrated through a set of conducted experiments, while the importance of the approach is discussed in the light of recent published literature.
Full-text available
The use of the computer as a model, metaphor, and modelling tool has tended to privilege the 'cognitive' over the 'affective' by engendering theories in which thinking and learning are viewed as information processing and affect is ignored or marginalised. In the last decade there has been an accelerated flow of findings in multiple disciplines supporting a view of affect as complexly intertwined with cognition in guiding rational behaviour, memory retrieval, decision-making, creativity, and more. It is time to redress the imbalance by developing theories and technologies in which affect and cognition are appropriately integrated with one another. This paper describes work in that direction at the MIT Media Lab and projects a large perspective of new research in which computer technology is used to redress the imbalance that was caused (or, at least, accentuated) by the computer itself.
Conference Paper
Full-text available
Emotion identification is beginning to be considered as an essential feature in human-computer interaction. However, most of the studies are mainly focused on facial expression classifications and speech recognition and not much attention has been paid until recently to physiological pattern recognition. In this paper, an integrative approach is proposed to emotional interaction by fusing multi-modal signals. Subjects are exposed to pictures selected from the International Affective Picture System (IAPS). A feature extraction procedure is used to discriminate between four affective states by means of a Mahalanobis distance classifier. The average classifications rate (74.11%) was encouraging. Thus, the induced affective state is mirrored through an avatar by changing its facial characteristics and generating a voice message sympathising with the user’s mood. It is argued that multi-physiological patterning in combination with anthropomorphic avatars may contribute to the enhancement of affective multi-modal interfaces and the advancement of machine emotional intelligence.
Conference Paper
Full-text available
Emotion identification has recently been considered as a key element in contemporary studies for advanced human-computer interaction. The achievement of this goal is usually attempted via methods incorporating facial expression and speech recognition, as well as, human motion analysis. In this paper it is attempted to fuse multi-modal physiological signals of the autonomic (skin conductance) and central nervous systems (EEG), through the use of appropriate feature extraction procedures discriminating emotional arousal modulations, to a neural network classifier. Thus, skin conductivity responses, evoked-related potential peaks, and delta frequency oscillatory patterns are analyzed for a comparatively large number of subjects exposed to different emotions, evoked by pictures selected from the International Affective Picture System. The achieved neural network classifications were encouraging. It was found that fear was successfully differentiated (100%), pleasant emotions differing in their arousal level were well distinguished (80%), but the discrimination of low arousing negative feelings such as melancholy was more difficult (70%). It is argued that physiological patterning of multimodal recordings may successfully contribute to the enhancement of human computer interaction and emotion aware computing.
Full-text available
Recent neuroscience findings demonstrate the fundamental role of emotion in the maintenance of physical and mental health. In the present study, a novel architecture is proposed for the robust discrimination of emotional physiological signals evoked upon viewing pictures selected from the International Affective Picture System (IAPS). Biosignals are multichannel recordings from both the central and the autonomic nervous systems. Following the bidirectional emotion theory model, IAPS pictures are rated along two dimensions, namely, their valence and arousal. Following this model, biosignals in this paper are initially differentiated according to their valence dimension by means of a data mining approach, which is the C4.5 decision tree algorithm. Then, the valence and the gender information serve as an input to a Mahalanobis distance classifier, which dissects the data into high and low arousing. Results are described in Extensible Markup Language (XML) format, thereby accounting for platform independency, easy interconnectivity, and information exchange. The average recognition (success) rate was 77.68% for the discrimination of four emotional states, differing both in their arousal and valence dimension. It is, therefore, envisaged that the proposed approach holds promise for the efficient discrimination of negative and positive emotions, and it is hereby discussed how future developments may be steered to serve for affective healthcare applications, such as the monitoring of the elderly or chronically ill people.
Emotion and attention heighten sensitivity to visual cues. How neural activation patterns associated with emotion change as a function of the availability of attentional resources is unknown. We used positron emission tomography (PET) and 15O-water to measure brain activity in male volunteers while they viewed emotional picture sets that could be classified according to valence or arousal. Subjects simultaneously performed a distraction task that manipulated the availability of attentional resources. Twelve scan conditions were generated in a 3 x 2 x 2 factorial design involving three levels of valence (pleasant, unpleasant and neutral), two levels of arousal and two levels of attention (low and high distraction). Extrastriate visual cortical and anterior temporal areas were independently activated by emotional valence, arousal and attention. Common areas of activation derived from a conjunction analysis of these separate activations revealed extensive areas of activation in extrastriate visual cortex with a focus in right BA18 (12, -88, -2) (Z=5.73, P < 0.001 corrected) and right anterior temporal cortex BA38 (42, 14, -30) (Z=4.03, P < 0.05 corrected). These findings support an hypothesis that emotion and attention modulate both early and late stages of visual processing.
Old, middle-aged and young persons of both genders were presented with slides containing pictorial stimuli that varied in emotional content. Each picture was rated on three dimensions: (1) valence; (2) arousal; and (3) dominance, using a 25-point scale. Heart rate, skin conductance, and forehead and cheek EMG were recorded during each slide presentation. The old and middle-aged groups showed greatly attenuated psychophysiological responses, compared to the young group. However, the old and middle-aged subjects used more extreme ratings than the young subjects on both the valence and arousal dimensions. Females were more valence-sensitive than males, but males in general used more extreme ratings of arousal than females. These results suggest a tendency to report increased felt emotion but decreased physiological response to emotional stimuli across the life span.
This commentary is a response to Interacting with Computers (Vol 14)—[Interacting Comput. 14 (2002) 119], [Interacting with Comput. 14 (2002) 141], [Interacting Comput. 14 (2002) 93]. Its aim is to discuss the role that neurophysiological measurements, such as EEG and MEG, may play in affective computing. The discussion is drawn upon the light of current experience and practice, as well as, advances envisaged in the fields of health informatics, telecommunications and biomedical engineering. It is explained why HCI research into interface evaluation and affective computing may be greatly enhanced by exploiting the underlying information of neurophysiological recordings.
Emotion and attention heighten sensitivity to visual cues. How neural activation patterns associated with emotion change as a function of the availability of attentional resources is unknown. We used positron emission tomography (PET) and 15O-water to measure brain activity in male volunteers while they viewed emotional picture sets that could be classified according to valence or arousal. Subjects simultaneously performed a distraction task that manipulated the availability of attentional resources. Twelve scan conditions were generated in a 3×2×2 factorial design involving three levels of valence (pleasant, unpleasant and neutral), two levels of arousal and two levels of attention (low and high distraction).Extrastriate visual cortical and anterior temporal areas were independently activated by emotional valence, arousal and attention. Common areas of activation derived from a conjunction analysis of these separate activations revealed extensive areas of activation in extrastriate visual cortex with a focus in right BA18 (12, −88, −2) (Z=5.73, P<0.001 corrected) and right anterior temporal cortex BA38 (42, 14, −30) (Z=4.03, P<0.05 corrected). These findings support an hypothesis that emotion and attention modulate both early and late stages of visual processing.